Research map / Optimization / Nonconvex and smooth optimization
Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimization
Wei Jiang, Gang Li, Yibo Wang, Lijun Zhang, Tianbao Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace the standard STORM correction with a block-sampling-aware error correction | MSVR block-value estimator · FCCO | estimation error | Improved |
| use the standard STORM error correction instead of the customized block-sampling correction (ablation) | FCCO block-value estimator · FCCO | sample complexity | No clear effect |
| replace the two-point function difference with a single-point Jacobian-vector product (ablation) | MSVR-SP · FCCO | sample complexity | No clear effect |
| apply MSVR-v1 instead of SOX | multi-task deep AUC maximization · CIFAR100 | loss | Improved |
| apply MSVR-v1 instead of SOX | multi-task deep AUC maximization · STL10, CIFAR10, MNIST, Fashion-MNIST, and SVHN | loss | No clear effect |
| apply MSVR-v2 instead of SOX and MSVR-v1 | multi-task deep AUC maximization · six image datasets | loss | Improved |
| apply MSVR-v3 instead of the other compared methods | multi-task deep AUC maximization · six image datasets | loss | Improved |
Closest papers by meaning
- A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimization (ICML 2025 · similarity 0.87)
- Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization (ICML 2024 · similarity 0.87)
- Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization (NeurIPS 2025 · similarity 0.87)
- Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient (ICML 2024 · similarity 0.86)
- Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions (NeurIPS 2024 · similarity 0.86)
- Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
